A Contextual-Bandit Oversight Game with Two-Sided Informational Asymmetry

• URL: http://arxiv.org/abs/2607.00155v1
• Date: Tue, 30 Jun 2026 20:30:01 GMT
• Title: A Contextual-Bandit Oversight Game with Two-Sided Informational Asymmetry
• Abstract summary: We study runtime human oversight of an AI agent when private information runs in both directions.<n>This is the kind of asymmetry that arises naturally when an autonomous robot or software agent has inspected a situation its human supervisor cannot directly assess.<n>We introduce a contextual-bandit team game with two-sided asymmetric information and a play/ask/trust/oversee interface.
• Score: 0.3384279376065155
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes. This is the kind of asymmetry that arises naturally when an autonomous robot or software agent has inspected a situation its human supervisor cannot directly assess. Building on Cooperative Inverse Reinforcement Learning (CIRL) and the Oversight Game, we introduce a contextual-bandit team game with two-sided asymmetric information and a play/ask/trust/oversee interface. The bandit structure removes physical state transitions and thereby yields exact one-shot characterizations that would remain conjectural in the full POMDP setting, though the common belief remains a dynamically controlled state across rounds. We give two one-shot characterizations, a team optimum and a behaviorally natural myopic rule, whose gap is a slab of avoidable harm: a region in which the AI privately knows the proposed action is harmful and shutdown would help, yet a myopic human, trusting her prior, declines to oversee. We show this gap is the price of non-credible oversight communication, and give a partial analysis of how it resolves dynamically over repeated rounds through passive learning and active signaling with a one-period-lagged oversight response.

Related papers

• ComBodied Agents: a New Paradigm of Human-Centric Agentic AI [121.60938707072069]
  We introduce Combodied Agents, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time.<n>We unify fragmented capabilities across personal assistants, health agents, AI companions, and adaptive human--AI systems into a closed loop.
  arXiv  Detail & Related papers  (2026-08-11T13:35:58Z)
• Runtime Action Interference for AI Control of AlphaStar in StarCraft II [20.538398143098117]
  We contribute emphruntime action interference (RAI), an AI control mechanism that preserves policy parameters while regulating action pacing and filtering configured action patterns.<n>RAI releases a proposed action only when its condition is satisfied and its content detector does not flag the action.<n>Our human evaluation shows that perceptions of an opponent controlled through RAI can vary substantially with the capability information presented to users.
  arXiv  Detail & Related papers  (2026-08-05T16:58:26Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy [9.553819152637493]
  We study a minimal control interface where an agent chooses whether to act autonomously (play) or defer (ask)<n>If the agent defers, the human's choice determines the outcome, potentially leading to a corrective action or a system shutdown.<n>Our analysis focuses on cases where this game qualifies as a Markov Potential Game (MPG), a class of games where we can provide an alignment guarantee.
  arXiv  Detail & Related papers  (2025-10-30T17:46:49Z)
• Observation Interference in Partially Observable Assistance Games [34.53170543153206]
  We study a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations.<n>We show that sometimes an optimal assistant must take observation-interfering actions, even when the human is playing optimally.<n>We show that if the human acts according to the Boltzmann model of irrationality, this can create an incentive for the assistant to interfere with observations.
  arXiv  Detail & Related papers  (2024-12-23T18:53:33Z)
• The Partially Observable Off-Switch Game [7.567880819525154]
  A wide variety of goals could cause an AI to disable its off switch because "you can't fetch the coffee if you're dead"<n>We introduce the Partially Observable Off-Switch Game (PO-OSG), a game-theoretic model of the shutdown problem with asymmetric information.<n>We find that in optimal play, even AI agents assisting perfectly rational humans sometimes avoid shutdown.
  arXiv  Detail & Related papers  (2024-11-25T14:09:48Z)
• Stochastic Principal-Agent Problems: Efficient Computation and Learning [25.637633553882985]
  A principal and an agent interact in a environment, each privy to observations about the state not available to the other. The model encompasses as special cases extensive-form games (EFGs) and approaches games of Markov decision processes (POMDPs) We show an efficient algorithm for an episodic reinforcement learning setting where transition probabilities are unknown.
  arXiv  Detail & Related papers  (2023-06-06T16:20:44Z)
• When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning [57.53138994155612]
  A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge is the presence of irreversible states which require external assistance to recover from, such as when a robot arm has pushed an object off of a table. We propose an algorithm that efficiently learns to detect and avoid states that are irreversible, and proactively asks for help in case the agent does enter them.
  arXiv  Detail & Related papers  (2022-10-19T17:57:24Z)
• Formalizing the Problem of Side Effect Regularization [81.97441214404247]
  We propose a formal criterion for side effect regularization via the assistance game framework. In these games, the agent solves a partially observable Markov decision process. We show that this POMDP is solved by trading off the proxy reward with the agent's ability to achieve a range of future tasks.
  arXiv  Detail & Related papers  (2022-06-23T16:36:13Z)
• A New Bandit Setting Balancing Information from State Evolution and Corrupted Context [52.67844649650687]
  We propose a new sequential decision-making setting combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which is not directly observable by the agent. We present an algorithm that uses a referee to dynamically combine the policies of a contextual bandit and a multi-armed bandit.
  arXiv  Detail & Related papers  (2020-11-16T14:35:37Z)
• Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry [66.82463322411614]
  The paper focuses on the problem of optimal ex ante persuasive signaling schemes, showing that symmetry is a crucial property for its solution. We show that an optimal ex ante persuasive scheme can be computed in time when players are symmetric and have affine cost functions.
  arXiv  Detail & Related papers  (2020-02-12T19:38:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.